© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116960
    Prev
    Next
    INDEX
    Explanations

    works for me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -0.07
    ลูกค้า
    -0.07
     systematically
    -0.07
    你
    -0.07
    Divider
    -0.06
    妳
    -0.06
     shoppers
    -0.06
     khoan
    -0.06
     প্রায়
    -0.06
     höhere
    -0.06
    POSITIVE LOGITS
     різних
    0.08
     разных
    0.08
     различных
    0.07
     различни
    0.07
     różnych
    0.06
    cych
    0.06
    different
    0.06
    異なる
    0.06
     commemorating
    0.06
     različ
    0.06
    Activations Density 0.007%

    No Known Activations